融合数值模式预报数据的深度学习PM2.5浓度预测模型

PM2.5污染问题是中国近年来引起广泛关注的环境问题,对PM2.5浓度进行预报有重要意义.传统的预报方法是基于空气动力学理论的数值模式预报方法.最近几年深度学习方法被广泛应用于PM2.5浓度预报问题.之前的深度学习预报方法主要是使用观测站的观测数据建立单点式的预报模型.本文使用ConvLSTM深度神经网络建立模型,在中国及周边区域的PM2.5数据集上实现了网格化的序列到序列预报.模型通过卷积模块提取空间特征,通过LSTM模块提取时间特征,适合解决PM2.5网格化预报问题.同时,模型中使用了再分析数据和模式数据两种不同来源的数据结合起来进行预报,融合了深度学习方法和传统数值模式方法.实验表明,模型的均方根误差比数值模式预报下降30.2%,具有良好的预报效果.     

数值预报中试系统设计与关键技术实现

气象数值预报模式是数值天气预报业务的重要基础，模式的研发改进需要在高性能计算环境中不断地开展模拟试验来检验评估预报效果。针对气象科学家手工编排批处理脚本开展数值模拟试验方式中存在的不便捷、耗时长、不可见、底层细节复杂、试验分析比对困难等问题，采用C/S架构，基于Python和工作流技术，设计实现了可视化界面交互“建模-计算-监控-分析-管理-共享”全流程集成应用的数值预报中试系统。应用结果表明，系统提升了模式研发试验效率和高性能计算机系统的易用性，在数值天气预报模式研发中试中发挥重要支撑作用，扩展性良好。     

对流天气预报系统的设计与实现

强对流天气内部蕴藏着巨大的能量,它具有突发性、强度大、持续时间短的特点。强对流天气发生时,常伴随有强雷暴、大风(风切变)、下击暴流、冰雹、龙卷等恶劣天气现象,严重影响航空的飞行安全。本研发计划旨在研制和集成国内外先进的强流天气分析预报方法,设计并建设终端区对流天气监测分析预报系统,以提升终端区强对流天气预报能力,适应我国民航事业快速发展的紧迫需求。系统功能主要包括终端区对流天气临近预报,终端区对流天气短时预报,起降条件与航路预报,预报产品检验与评估。     

基于韦伯模型的风场储能容量计算

风能的间歇性和波动性给风电大规模并网带来了许多不利影响,在风电场出口处配置储能系统可以有效抑制风电波动、调节并网功率的变化率,提高风电场并网运行的可靠性、稳定性。文章分析了风电场风速的模型,风力发电机输出模型,运用韦伯函数建立风速分布模型,采用概率论期望的思想,计算储能系统功率容量。通过模拟仿真实验,得出满足电力系统要求的合理风储比。在满足我国风电并网标准的条件下,尽可能地减小储能系统规模,并利用实际风电场数据加以分析验证。     

固体火箭发动机比冲预示的神经网络仿真研究

运用BP和RBF神经网络方法和Matlab6.5工具软件建立了小样本数据条件下的固体火箭发动机比冲的神经网络预测模型,并将两种神经网络预报的效果进行了比较。两种网络较好的预报效果,表明建立的预测模型是合理的。在此基础上,提出了与之相应的预报误差控制方法及其新型号发动机比冲预测的选模判据。数值实验结果表明,所提供的网络模型可在小样本数据条件下实现发动机比冲性能的高精度预测。     

基于流水线模式的河系径流预报并发计算研究

在河系径流预报计算中,一方面受单站水文过程计算复杂性影响,另一方面下游站点依赖上游关联节点,现有洪水预报系统在河系预报计算时多采用串联模式进行计算。这在河流系预报节点较多、模型方法略为复杂时,计算效率较低。为突破河系径流预报计算效率瓶颈,本研究引入流水线并行模式,对河系径流预报站点初始化、单元产汇流计算、河道洪水演算、校正分析等模块进行拆解,构建流水线式工作站,将径流预报站点按水力联系连续入站,实现河系节点集径流过程的平行并发计算。选取淮河正阳关以上流域50余断面进行了模拟试验,结果表明：研究构建的并发计算方法计算结果可靠,较串行结构效率提升超3倍,可满足洪水预报实时性要求、尤其适用于B/S模式对系统响应效率的需求。     

神经网络在经济市场波动率建模与预测中的应用

本文提出一种马尔可夫交换人工神经网络，应用于经济市场中的黄金市场的波动性建模与预测。本文所提出的模型在条件波动过程的动态性与传统神经网络模型相比，在预测能力上有所不同。在本文中，应用此类模型来检验黄金收益率的波动性。对绝对误差、均方误差和均方根误差准则加以评估，并且在相同精度下进行改良的DieboldMariano测试。为黄金市场日收益的预测提供了一个实证应用，结果表明，该方法在模拟和预测国际黄金日收益波动性方面具有较好的效果。     

基于卷积门循环单元和气象雷达图像的临近降水预报

现有的深度神经网络预测模型主要是通过学习单一高度下的雷达回波图像序列的特征预测未来时间段回波序列.然而,这种模型并不能直接预测目标站点未来一段时间内的降水量.鉴于此,提出了一种基于卷积门循环单元(Con-volutional Gated Recurrent Unit,ConvGRU)神经网络的临近降水预报模型.对目标站点不同高度的雷达回波图像做卷积,同一高度的卷积图像通过GRU(Gated Recurrent Unit)学习云团运动过程中的时序特征,将不同高度时序图像的学习特征聚合到全连接层中进行训练,输出目标站点未来1h～2h的降水量.实验分析表明,该模型在未来1h～2h的降水预报中取得了较好的预报精度.     

实况气象资料与遗传蚁群算法相结合的航迹规划研究

利用国家气象中心提供的T106实况数值预报产品,采用预报指数模式计算飞机积冰、颠簸等潜在威胁区域,进而建立气象威胁场;在气象威胁场基础上利用遗传蚁群算法进行航迹规划,使无人机在满足约束条件下以最小代价规避气象威胁区域;仿真结果表明,该航迹规划方法可行、高效,能够准确、快速寻优到最优航迹,具有一定的实用价值。     

人工神经网络在小区域强降水预报应用研究

针对小区域强降水的非线性性质,利用T213数值预报产品,通过人工神经网络建模方法进行预报释用,对数量众多预报因子采用经验正交分解方法,浓缩大量因子的有效信息,建立逐日小区域强降水的人工神经网络预报模型.运用与实际业务预报相同的方法进行逐日预报试验,并与回归预报模型进行比较.结果表明,人工神经网络预报模型对小区域强降水的TS评分为0.67,而逐步回归模型的TS评分仅为0.20.由此可见,人工神经网络具有较强的处理非线性问题能力,在小区域强降水应用中具有更好的预报效果.     

Locally recurrent neural networks for wind speed prediction using spatial correlation

This paper deals with the wind speed prediction in wind farms, using spatial information from remote measurement stations. Owing to the temporal complexity of the problem, we employ local recurrent neural networks with internal dynamics, as advanced forecast models. To improve the prediction performance, the training task is accomplished using on-line learning algorithms based on the recursive prediction error (RPE) approach. A global RPE (GRPE) learning scheme is first developed where all adjustable weights are simultaneously updated. In the following, through weight grouping we devise a simplified method, the decoupled RPE (DRPE), with reduced computational demands. The partial derivatives required by the learning algorithms are derived using the adjoint model approach, adapted to the architecture of the networks being used. The efficiency of the proposed approach is tested on a real-world wind farm problem, where multi-step ahead wind speed estimates from 15 min to 3 h are sought. Extensive simulation results demonstrate that our models exhibit superior performance compared to other network types suggested in the literature. Furthermore, it is shown that the suggested learning algorithms outperform three gradient descent algorithms, in training of the recurrent forecast models.     

Forecasting wind speed using empirical mode decomposition and Elman neural network

Because of the chaotic nature and intrinsic complexity of wind speed, it is difficult to describe the moving tendency of wind speed and accurately forecast it. In our study, a novel EMD–ENN approach, a hybrid of empirical mode decomposition (EMD) and Elman neural network (ENN), is proposed to forecast wind speed. First, the original wind speed datasets are decomposed into a collection of intrinsic mode functions (IMFs) and a residue by EMD, yielding relatively stationary sub-series that can be readily modeled by neural networks. Second, both IMF components and residue are applied to establish the corresponding ENN models. Then, each sub-series is predicted using the corresponding ENN. Finally, the prediction values of the original wind speed datasets are calculated by the sum of the forecasting values of every sub-series. Moreover, in the ENN modeling process, the neuron number of the input layer is determined by a partial autocorrelation function. Four prediction cases of wind speed are used to test the performance of the proposed hybrid approach. Compared with the persistent model, back-propagation neural network, and ENN, the simulation results show that the proposed EMD–ENN model consistently has the minimum statistical error of the mean absolute error, mean square error, and mean absolute percentage error. Thus, it is concluded that the proposed approach is suitable for wind speed prediction.     

基于GRNN全信息神经网络的超短期风速预测研究

为了更好地研究风功率预测,风速预测显得至关重要.国内神经网络文献均只表现出了短期风速预测,而对于超短期风速预测的神经网络数学模型却相对稀少.引入了GRNN神经网络,详细说明了该方法的超短期风速预测原理并建立了数学模型;为了使超短期风速预测精度有一个良好的对比性分析,将影响风电输出功率的各NWP(numerical weather prediection)信息(包括风速、风向、气温、气压)进行组合,以国内某风电场2014年5月份的各NWP数据进行算例分析,实验结果表明,GRNN全信息神经网络可以达到很好的预测精度,而且运算网络的稳定性甚优.     

EMD与NARX神经网络的风电场总功率组合预测

探索构建对风电场总功率进行直接预测的高精度组合预测算法。考虑到风速的非平稳性导致风电总功率表现为非平稳时间序列,采用NARX神经网络作为初步预测模型,提出了经验模态分解与NARX神经网络相结合的混合预测模型。对风电场总功率非平稳时间序列进行经验模态分解,得到不同频带本征模式分量的平稳序列。对不同频带的平稳分量建立相应的NARX神经网络预测模型,并将各分量模型的预测值进行等权求和得到最终预测值。此外,为研究不同时间间隔对预测结果的影响,采用某大型风电场时间间隔为5 min与15 min的数据进行实验。预测结果表明,提出的组合预测模型适合于总功率预测,其预测效果比传统模型的效果更佳,且时间间隔为5 min的数据比时间间隔为15 min的数据预测精度更高。     

Weather analysis using ensemble of connectionist learning paradigms

This paper presents a comparative analysis of different connectionist and statistical models for forecasting the weather of Vancouver, Canada. For developing the models, one year's data comprising of daily temperature and wind speed were used. A multi-layered perceptron network (MLPN) and an Elman recurrent neural network (ERNN) were trained using the one-step-secant and Levenberg–Marquardt algorithm. Radial basis function network (RBFN) was employed as an alternative to examine its applicability for weather forecasting. To ensure the effectiveness of neurocomputing techniques, the connectionist models were trained and tested using different datasets. Moreover, ensembles of the neural networks were generated by combining the MLPN, ERNN and RBFN using arithmetic mean and weighted average methods. Subsequently, performance of the connectionist models and their ensembles were compared with a well-established statistical technique. Experimental results obtained have shown RBFN produced the most accurate forecast model compared to ERNN and MLPN. Overall, the proposed ensemble approach produced the most accurate forecast, while the statistical model was relatively less accurate for the weather forecasting problem considered.     

基于Gradient Boosting算法的ERMS辐射数据预测

影响核辐射监测站点辐射监测HPIC剂量率实时数据准确性的组成因素多且复杂,如自然因素的降雨、温湿度、风向及太阳辐射等,客观因素的设备异常及放射性状况等;以致在实际应用中发现辐射监测状态异常时,很难分析出是什么原因导致的监测数据偏离.结合ERMS海量历史辐射序列监测数据,深入挖掘降雨、温湿度、气压、风向、太阳辐射天顶方向电子量及周边各站点辐射数值等特征因子集,基于Gradient Boosting算法（简称GB算法）建立起HPIC剂量率辐射数据的在线预测模型,有效融合自然特征因子,降低了自然因子对HPIC剂量率辐射监测数值异常的分析及判读的干扰作用,提高了对ERMS辐射异常发现的辅助判断能力及维保效率.     

Short-Term Wind Speed Prediction Using Signal Preprocessing Technique and Evolutionary Support Vector Regression

Short-term wind speed prediction is beneficial to guarantee the safety of wind power utilization and reduce the cost of wind power generation. As a kind of the powerful artificial intelligent algorithms, support vector regression (SVR) has been successfully employed in solving forecasting problems. However, due to the intrinsic complexity and multi-patterns of wind speed fluctuations, it is regarded as one of the most challenging applications for wind speed prediction. To alleviate the influence of complexity and capture these different patterns, this study proposes a novel approach named SIE–WDA–GA–SVR for short-term wind speed prediction, which applies the seasonal information extraction (SIE) and wavelet decomposition algorithm (WDA) into hybrid model that integrates the genetic algorithm (GA) into SVR. First, the proposed approach uses SIE to decompose the original wind speed into seasonal and trend components, and the seasonal indices are calculated by SIE. Second, the proposed approach uses WDA to decompose the trend component into both the approximate and the detailed scales. Third, the proposed approach uses GA–SVR to forecast the approximated and detailed scales, respectively. Then, the prediction values of the trend component can be obtained by integrating the prediction values of the approximated scale into the prediction values of the detailed scale. By integrating the seasonal indices into the prediction values of trend component, we can obtain the final forecasting results of the original wind speed. Moreover, the partial autocorrelation function is used to determine the number of input dimension for the SVR, and the GA is used to select the parameters of the SVR. Four real wind speed datasets are used as test samples to verify the proposed approach. Experimental results indicate that the proposed approach outperforms other benchmark models in four statistical error measures, and can improve the forecasting accuracy of wind speed.     

Grouped Gaussian processes for solar power prediction

We consider multi-task regression models where the observations are assumed to be a linear combination of several latent node functions and weight functions, which are both drawn from Gaussian process priors. Driven by the problem of developing scalable methods for forecasting distributed solar and other renewable power generation, we propose coupled priors over groups of (node or weight) processes to exploit spatial dependence between functions. We estimate forecast models for solar power at multiple distributed sites and ground wind speed at multiple proximate weather stations. Our results show that our approach maintains or improves point-prediction accuracy relative to competing solar benchmarks and improves over wind forecast benchmark models on all measures. Our approach consistently dominates the equivalent model without coupled priors, achieving faster gains in forecast accuracy. At the same time our approach provides better quantification of predictive uncertainties.

     

基于聚类的超闭球算法短期风速预测研究

具有较高精度的超短期风速预测有着重要的作用,它对建立和保障并网运行风电场风电功率预测预报系统有着举足轻重的作用.但是,由于风速的影响因素较多,且存在着巨大的波动性、随机性,以及较高的自相关性.这些因素,极大地影响了传统的风速预测方法.因此,探究一种短期风速预测方法是十分必要的,此方法以聚类的小脑超闭球算法为基础,此超闭球方法,对减少数据输入的地址碰撞有着很好的作用,提高了学习速度,另通过模糊聚类对输入数据确定节点数和节点值,提高了学习精度.仿真结果证明基于聚类的小脑超闭球网络相比应用较为成熟的BP神经网络等能很好地预测未来1h风速.     

A hybrid VMD–BiGRU model for rubber futures time series forecasting

As one of the four major industrial raw materials in the world, natural rubber is closely related to the national economy and people’s livelihood. The analysis of natural rubber price and volatility can give hedging guidance to manufacturers and provide investors with uncertainty and risk information to reduce investment losses. To effectively analyses and forecast the natural rubber’s price and volatility, this paper constructed a hybrid model that integrated the bidirectional gated recurrent unit and variational mode decomposition for short-term prediction of the natural rubber futures on the Shanghai Futures Exchange. In data preprocessing period, time series is decomposed by variational mode decomposition to capture the tendency and mutability information. The bidirectional gated recurrent unit is introduced to return the one-day-ahead prediction of the closing price and 7-day volatility for the natural rubber futures. The experimental results demonstrated that: (a) variational mode decomposition is an effective method for time series analysis, which can capture the information closely related to the market fluctuations; (b) the bidirectional neural network structure can significantly improve the model performance both in terms of fitting performance and the trend prediction; (c) a correspondence was found between the predicted target, i.e., the price and volatility, and the intrinsic modes, which manifested as the impact of the long-term and short-term characteristics on the targets at different time-scales. With a change in the time scale of forecasting targets, it was found that there was some variation in matching degree between the forecasting target and the mode sub-sequences.